Mastering Autonomous Assembly in Fusion Application with Learning-by-doing: a Peg-in-hole Study

TL;DR

This paper introduces a reinforcement learning approach that integrates multi-sensor data to improve robotic peg-in-hole assembly accuracy in fusion applications, demonstrating superior performance in realistic, uncertain environments.

Contribution

It advances the field by focusing on enhancing DNN architecture and multi-sensor fusion for improved robotic assembly in fusion environments.

Findings

Achieved 0.1 mm accuracy in peg-in-hole tasks

Outperformed existing methods in uncertain conditions

Validated in realistic experimental settings

Abstract

Robotic peg-in-hole assembly represents a critical area of investigation in robotic automation. The fusion of reinforcement learning (RL) and deep neural networks (DNNs) has yielded remarkable breakthroughs in this field. However, existing RL-based methods grapple with delivering optimal performance under the unique environmental and mission constraints of fusion applications. As a result, we propose an inventively designed RL-based approach. In contrast to alternative methods, our focus centers on enhancing the DNN architecture rather than the RL model. Our strategy receives and integrates data from the RGB camera and force/torque (F/T) sensor, training the agent to execute the peg-in-hole assembly task in a manner akin to human hand-eye coordination. All training and experimentation unfold within a realistic environment, and empirical outcomes demonstrate that this multi-sensor fusion approach excels in rigid peg-in-hole assembly tasks, surpassing the repeatable accuracy of the robotic arm utilized--0.1 mm--in uncertain and unstable conditions.